# Artificially Evolved Chunks for Morphosyntactic Analysis

## TL;DR

This paper presents an evolutionary, language-agnostic method for automatically extracting chunks from dependency treebanks, which improve morphosyntactic analysis tasks like POS tagging and dependency parsing across multiple languages.

## Contribution

It introduces a novel evolutionary approach for chunk extraction and demonstrates its utility in enhancing various morphosyntactic tasks within a multi-task learning framework.

## Key findings

- Chunks improve POS tagging accuracy.
- Chunks enhance dependency parsing performance.
- Method is effective across multiple languages.

## Abstract

We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks. We evaluate these chunks on a number of morphosyntactic tasks, namely POS tagging, morphological feature tagging, and dependency parsing. We test the utility of these chunks in a host of different ways. We first learn chunking as one task in a shared multi-task framework together with POS and morphological feature tagging. The predictions from this network are then used as input to augment sequence-labelling dependency parsing. Finally, we investigate the impact chunks have on dependency parsing in a multi-task framework. Our results from these analyses show that these chunks improve performance at different levels of syntactic abstraction on English UD treebanks and a small, diverse subset of non-English UD treebanks.